Clustering in Knowledge Embedded Space

Abstract

Cluster analysis is a fundamental technique in pattern recognition. It is difficult to cluster data on complex data sets. This paper presents a new algorithm for clustering. There are three key ideas in the algorithm: using mutual neighborhood graphs to discover knowledge and cluster data; using eigenvalues of local covariance matrixes to express knowledge and form a knowledge embedded space; and using a denoising trick in knowledge embedded space to implement clustering. Essentially, it learns a new distance metric by knowledge embedding and makes clustering become easier under this distance metric. The experiment results show that the algorithm can construct a quality neighborhood graph from a complex and noisy data set and well solve clustering problems.

Cite

Text

Zhang et al. "Clustering in Knowledge Embedded Space." European Conference on Machine Learning, 2003. doi:10.1007/978-3-540-39857-8_43

Markdown

[Zhang et al. "Clustering in Knowledge Embedded Space." European Conference on Machine Learning, 2003.](https://mlanthology.org/ecmlpkdd/2003/zhang2003ecml-clustering/) doi:10.1007/978-3-540-39857-8_43

BibTeX

@inproceedings{zhang2003ecml-clustering,
  title     = {{Clustering in Knowledge Embedded Space}},
  author    = {Zhang, Yungang and Zhang, Changshui and Wang, Shijun},
  booktitle = {European Conference on Machine Learning},
  year      = {2003},
  pages     = {480-491},
  doi       = {10.1007/978-3-540-39857-8_43},
  url       = {https://mlanthology.org/ecmlpkdd/2003/zhang2003ecml-clustering/}
}